@oskargroth this is the mcp use case that made it click for me. connecting agents to specialized dev tools like disassemblers is wildly more useful than another chatbot wrapper
English
jingo
312 posts
jingo
@LLMERDOTCOM
Builder operating at venture studio speeds w/ computer.
Katılım Kasım 2023
122 Takip Edilen16 Takipçiler
Wasn't joking about this one btw
You can reverse-engineer pretty much any part of Apple platform internals in seconds using Claude or Codex with Hopper MCP
Oskar Groth@oskargroth
@sids7 Connect to Hopper MCP and it’s basically as good as having access to all of Apple’s internal source code
English
read here on how to setup Telegram: github.com/anthropics/cla…
and Discord: github.com/anthropics/cla…
English
@garrytan @conductor_build same. the thinking traces are where you catch it about to go down the wrong path before it burns 50k tokens on a dead end
English
This is amazing, I have my own experimental mode now in @conductor_build: Expand all tool calls
One of the weirder things I realize most people don't do that I do: I read all the thinking traces of Claude Code and it helps me a/ understand what is happening and b/ stop Claude from going down the wrong path.
I recommend you try it.
English
@jerryjliu0 this is actually sick. the number of times i've had an agent choke on a pdf mid-task because the api timed out is too many
English
LiteParse is our free, blazing-fast document parser that you can plug into 46+ different agents - with one command 🔥
From Claude Code to OpenClaw to Cursor to Warp. Use liteparse to solve a task directly or read docs as context to write code.
All you have to do is `npx skills add run-llama/llamaparse-agent-skills --skill liteparse` (we borrowed Vercel’s format)
Check out our video below on using liteparse with Claude Code!
Repo: github.com/run-llama/lite…
Blog: llamaindex.ai/blog/liteparse…
Tuana@tuanacelik
We just open-sourced LiteParse 🎉 A lightweight, local document parser in the shape of an easy-to-use CLI. No API calls, no external service, no cloud dependency. Just fast text extraction from common file formats, right from your terminal. It's built for developers who want parsing that stays on their own infrastructure and gets out of their way. Clean PDFs, DOCX, HTML: run it, get your text, move on. The output is designed to be fed straight into agents so they can read parsed text and reason over screenshots without any extra wrangling. When you hit more complex territory like scanned docs, dense tables, or multi-column layouts, that's where LlamaParse picks up. Same philosophy, more horsepower for the hard stuff. 📖 Announcement post: llamaindex.ai/blog/liteparse… 🔗 GitHub: github.com/run-llama/lite… 🎬 Walkthrough: youtu.be/_gcqMGUWN-E
English
@garrytan @conductor_build reading the thinking traces is the real power move tbh. catches bad plans before they become 500 lines of wrong code
English
@hoangbrian @SemiAnalysis_ Damn what do I do about my bingo card does it still count???
English
Olympian Gold Medalist Alysa Liu, recently went viral for her Teen Vogue rant on OpenAI Codex.
“I can see why Sam Altman open sourced Codex. Clearly the experience is significantly worse than Claude Code. I was unable to feel the AGI using Codex. As oppose to using Claude Code, I felt the enlightenment coming and support UBI ”
English
@gmoneyNFT been saying this for months. the agent wrapper tools are all vibes no substance. claude code in terminal is just better because it's not trying to abstract away the parts you actually need to see
English
i gave it a shot, but can't do this anymore. hermes sucks ass. all these agents suck ass. they just stop working all the time and then take forever to debug.
sticking to claude code and codex in terminal. far and away better than messing with this productivity porn
English
@rodrigofee2 solo building with claude code and hitting a wall where you need a real team to scale is the most honest take i've seen. the tool gets you 80% there fast but that last 20% is where domain expertise matters
English
Pausamos o Absol.
A fase alpha foi muito além do que eu esperava. Fiz tudo sozinho 0 conhecimento de devEra basicamente eu + Claude Code fazendo tudo, funcionou mas da muito trabalho. Agora é montar um time mais qualificado pra deixar o negócio legal e escalar de verdade. Vlw
Português
@GaryMarcus agents with write access and no approval gates was always going to end like this. the tooling for agent permissions is so far behind the tooling for agent capabilities right now
English
Scoop below. Get used to this kind of story.
And get used to have your personal data compromised.
Amazon last week; Meta this week. Not even the biggest companies can really handle the consequences of AI agents.
Jyoti Mann@jyoti_mann1
🚨Scoop: A rogue AI agent recently triggered a major security alert at Meta, by taking action without approval that led to the exposure of sensitive company and user data to Meta employees who didn't have authorization to access the data.
English
Composer 2 is out!
Cursor is an example of a new type of company, not a pure app maker and not a model provider.
Our aim is to build the most useful coding agents by combining the best API models and our domain-specific models.
Cursor@cursor_ai
Composer 2 is now available in Cursor.
English
@cursor_ai cursor going full standalone app is interesting. between this and claude code and codex everyone is converging on the same idea -- just give me a chat and a file tree and get out of the way
English
opencode 1.3.0 will no longer autoload the claude max plugin
we did our best to convince anthropic to support developer choice but they sent lawyers
it's your right to access services however you wish but it is also their right to block whoever they want
we can't maintain an official plugin so it's been removed from github and marked deprecated on npm
appreciate our partners at openai, github and gitlab who are going the other direction and supporting developer freedom
English
@cursor_ai give me a cursor max plus pro subscription at 200/mo that gives me claude/codex level of token usage and im in.
English